Ideas Factories

Scatter plot

Photo by Johny Goerend on Unsplash

Bourscheid castle in the north of Luxembourg

A pile of rocks ceases to be a rock pile when somebody contemplates it with the idea of a cathedral in mind…
— Antoine Saint-Exupéry

Ingest data

gdp and innovation rank by country and year

# Load csv data file
url_root <- "https://raw.githubusercontent.com/UN-AVT/kamino-source/main/sources/0-shared/data/"

url_file1 <- "ideas-factories/gdp-per-person-employed-constant-ppp.csv"
url1 <- paste0(url_root, url_file1)

url_file2 <- "ideas-factories/global-innovation-index.csv"
url2 <- paste0(url_root, url_file2)

df_gdp<- read.csv(url1, header = TRUE, stringsAsFactors = FALSE)
df_gdp

df_gii<- read.csv(url2, header = TRUE, stringsAsFactors = FALSE)
df_gii

Wrangle data

filter, merge, enrich, select, clean, rename, wow!

df_gdp_filtered <- df_gdp %>% filter(Year == 2020)

df_gii_filtered <- df_gii %>% filter(Indicator == 'Global Innovation Index')
df_gii_filtered <- df_gii_filtered %>% filter(Subindicator.Type == 'Rank')
df_gii_filtered <- df_gii_filtered %>% select(c(Country.ISO3, Country.Name, X2020))

df_combined <- merge(df_gdp_filtered, df_gii_filtered, by.x='Code', by.y='Country.ISO3')

df_combined$REGION <- countrycode(df_combined$Code, origin='iso3c', destination='un.region.name')

df_combined <- df_combined %>% select(c(Code, Entity, GDP.per.person.employed..constant.2017.PPP..., X2020, REGION))

df_combined <- df_combined[complete.cases(df_combined), ]

df_final <- df_combined %>%
  rename(ISO3 = Code,
         COUNTRY = Entity,
         GDP = GDP.per.person.employed..constant.2017.PPP...,
         GII = X2020)

df_final <- df_final %>% rename_with(toupper)
df_final

Plot Scatter

data points with smoothing

theme_opts <- theme(
    text = element_text(family = "inconsolata", size = 16), 
    plot.title = element_text(color = "black", size = 16, face = "bold"),
    plot.subtitle = element_text(color = "black", size = 12),
    plot.caption = element_text(color = "#555555", size = 10),
    # axis.title.x = element_blank(),
    # axis.title.y = element_blank(),
    # axis.text.x = element_text(vjust = 12),
    panel.border = element_blank(),
    panel.background = element_blank(),
    # panel.grid.minor = element_blank(),
    # panel.grid.major = element_blank(),
    legend.position='top'
)

# Plot
v1 <- ggplot(df_final, aes(x = GDP, y = GII)) + 
  geom_point(aes( fill = REGION, color = REGION), size = 4, shape = 21) +
  geom_smooth(formula = y ~ x, method="loess", se = FALSE, linetype = 'solid', size = 2, color = '#82A0C2') + # "lm", "glm", "gam", "loess" 
  scale_x_continuous() +
  scale_y_continuous() +
  scale_y_reverse() +
  labs( title = "Ideas Factories",
        subtitle = "Global Innovation and GDP",
        caption = "Source: Cornell INSEAD WIPO",
        x = "GDP per Person Employed, constant PPP, 2020",
        y = "Global Innovation Index, 2020") +
  theme_bw() +
  theme_opts

girafe(ggobj = v1, width_svg = 16, height_svg = 12,
       options = list(opts_sizing(rescale = TRUE, width = 0.75))
)

Plot with annotations

some narrative to help tell the story

v2 <- v1 + 
      annotate("text", x = 200000, y = 30, 
              label = "European countries presented high GDP\ndespite the low Global Innovation Index", 
              hjust = "left", vjust = 1, color = "#333333", size = 4, fontface = 1) +
      annotate("text", x = 45000, y = 110, 
               label = "African countries presented low GDP despite\nthe high Global Innovation Index",
               hjust = "left", vjust = 1, color = "#333333", size = 4, fontface = 1) 

girafe(ggobj = v2, width_svg = 16, height_svg = 12,
       options = list(opts_sizing(rescale = TRUE, width = 0.75))
)

References

The citations and data sources used for this case

Narrative Inspiration: The Economist, Ideas Factories, Global innovation and GDP
Data sources: Global Innovation Index, GO